Making default pdf extracting more robust (#17675)

Co-authored-by: Mattermod <mattermod@users.noreply.github.com>

services/docextractor/pdf.go

@@ -5,6 +5,7 @@ package docextractor
 
 import (
 	"bytes"
+	"errors"
 	"fmt"
 	"io"
 	"io/ioutil"
@@ -25,7 +26,13 @@ func (pe *pdfExtractor) Match(filename string) bool {
 	return supportedExtensions[extension]
 }
 
-func (pe *pdfExtractor) Extract(filename string, r io.ReadSeeker) (string, error) {
+func (pe *pdfExtractor) Extract(filename string, r io.ReadSeeker) (out string, outErr error) {
+	defer func() {
+		if r := recover(); r != nil {
+			out = ""
+			outErr = errors.New("error extracting pdf text")
+		}
+	}()
 	f, err := ioutil.TempFile(os.TempDir(), "pdflib")
 	if err != nil {
 		return "", fmt.Errorf("error creating temporary file: %v", err)

services/docextractor/pdf_test.go

@@ -0,0 +1,36 @@
+// Copyright (c) 2015-present Mattermost, Inc. All Rights Reserved.
+// See LICENSE.txt for license information.
+
+package docextractor
+
+import (
+	"bytes"
+	"testing"
+
+	"github.com/mattermost/mattermost-server/v5/utils/testutils"
+	"github.com/stretchr/testify/require"
+)
+
+func TestPdfEmptyFile(t *testing.T) {
+	extractor := pdfExtractor{}
+	_, err := extractor.Extract("test.pdf", bytes.NewReader([]byte{}))
+	require.Error(t, err)
+}
+
+func TestPdfFile(t *testing.T) {
+	extractor := pdfExtractor{}
+	contentText := "This is a simple document that contains some text."
+	content, err := testutils.ReadTestFile("sample-doc.pdf")
+	require.NoError(t, err)
+	extractedText, err := extractor.Extract("sample-doc.pdf", bytes.NewReader(content))
+	require.NoError(t, err)
+	require.Equal(t, contentText, extractedText)
+}
+
+func TestWrongPdfFile(t *testing.T) {
+	extractor := pdfExtractor{}
+	content, err := testutils.ReadTestFile("sample-doc.docx")
+	require.NoError(t, err)
+	_, err = extractor.Extract("sample-doc.pdf", bytes.NewReader(content))
+	require.Error(t, err)
+}